Why creating overrides?
A predictive model is based on historical data: it analyzes past data to predict the future.
In the Customer fit model, the segment of a lead (very good, good, medium, low) is defined by the model according to the result returned by historical conversions. However, you may want to override the model to force the segment of some leads based on one or more traits for a few reasons:
- You have not historically converted a lot of Enterprise companies but you are going up market and want to make sure Enterprise leads are routed to Sales.
- You have converted some small companies in the past but you do not want to waste your Sales team skill on companies with less than 50 employees.
- There isn't clear evidence from your data for which job roles and titles are the best but you want to boost some specific job titles based on your Sales team feedback.
For example, your company has not converted a lot of leads from Enterprise companies, therefore the model "naturally" scores them medium because your historical data say these leads don't convert well. However, you still want to prioritize these leads as very good for your Sales team to go after. To do so, you would apply an override like "If the company size of the lead is more than XXXX, then it should be scored very good" [regardless of what the historical data says].
Which overrides to create?
⏩ Follow the tips in this article: A few tips to create relevant overrides
How to add an override to a live model?
Pre-requisites
- You have the permissions of the Architect or Admin role
- You know what a Computation is
Step 1: Duplicate the live model
- Go to the Data Studio (studio.madkudu.com)
- Duplicate the model marked as "live" (live models cannot be edited directly)
- Name the duplicated model how you want
Step 2: Create the override
-
- In the model, Model > Overrides
- In the model, Model > Overrides
- Click on Create new rule
- Select Form mode (preferred)
- Select Advanced mode if you need a complex logic not supported by the form node. You'll need to use SQL conditions like you would in a WHERE statement.
- Select the Computation, condition, value, rule and segment to create an override
- Check the box Case insensitive to make the override work regardless of upper/lower cases in the value.
- Click on AND to add a condition
- If you need an OR condition, just create another override
- Click on Save.
After you save, you will notice that your overrides are reordered.
This reordering reflects how they will be taken into account by the model:
- Overrides with a rule should be come first
- Within those, overrides are ordered depending on which segment they place leads in:
- 1 low > 2 medium > 3 good > 4 very good
- Overrides with a rule should at most be come second
- Within those, overrides are ordered depending on which segment they place leads in:
- 1 low > 2 medium > 3 good > 4 very good
- Overrides with a rule should at least be come last
- Within those, overrides are ordered depending on which segment they place leads in:
- 1 very good > 2 good > 3 medium > 4 low
Only one of each type of rule is applied on a lead (in the order listed above). If a rule should be is applied, all other rules are ignored. A rule should at least be can only upgrade a lead up to the limit defined by a rule should at most be (if applied).
You cannot manually reorder the overrides, and it is by design: if 2 overrides, one downgrading to low and another one upgrading to very good, touch a lead, we estimate it is a great risk to send to Sales a lead with a downgrading attribute (being a spam, being a student...), even if they have other good upgrading attributes (belongs to a large company, is in the target industry...). That's why downgrading overrides are applied first, in order not to break trust in the model by sending low-quality leads to your Sales.
Step 3: Assess the impact of the override
You would want to make sure this override is not boosting or penalizing too many leads in a specific segment degrading the performance of the model.
To compare the impact of the override you just added on the training dataset
Click on the Overrides impact analysis button to look at the performance on the training dataset. The difference in performance between the tab Thresholds and this tab is the impact of all the overrides on the performance.
To compare the impact of the override you just added on the validation dataset
Open the live model on your browser, head to the Review > Performance tab, and compare the performance graph you see to the Performance tab of the model you added to override.
Step 4: Deploy override
Keep these considerations in mind when deploying overrides:
- All your Leads, Contacts, or Accounts that are usually scored by MadKudu will get rescored with the next batch scoring within the next 4-12 hours (see when the next Analysis then Sync process should run in the Processes Page).
- Adding, editing, or deleting overrides that increase or decrease prospect scores may trigger automated workflows in your CRM which are based on the customer fit or lead grade score (like your MQL workflow).
When you are ready, go to the Deploy tab
- If the live model you are editing is flagged "Live as Standard", then go into the first sub-tab "deploy as standard" and click Primary deploy
- If the live model you are editing is flagged "Live as Multi-fit", please submit a support ticket to our support team, and we'll help you with that.
Well done!
F.A.Q
If a lead falls in an override "should be low" and another "should be very good", which override is applied?
Overrides penalizing the score of a lead or account has priority over an override boosting the score.
Ex: There is
- an override "IF country in Mexico, THEN should be low"
- and an override "IF employees > 10,000 AND industry = Internet Software & Services THEN should be very good"
Then a 10k software company based in Mexico would be scored low, regardless of how the override are listed in the interface.
I don't see my CRM field in the picklist, what should I do?
The picklist contains Computations and not the list of your CRM fields. To create a computation from your CRM field, please follow the following steps
- Make sure your CRM field is pulled in the MadKudu platform
- Map your CRM field in the Attribute mapping which will make it available to the Data Science Studio
- Create a computation and click Deploy
- In the model where you'd like to add this override, in the Overview, on the bottom right click "Reload computations"
- After the reload is finished, you will see the Computation name using your CRM field available to use in an Override.
I created a computation but I don't see it in the picklist, what should I do?
Make sure you have released the computation, following Step 2 of this article.